AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Ssh Async

skill-02loveslollipop-opencrow-ssh-async · by 02loveslollipop

Maintain persistent asynchronous SSH sessions with bidirectional input/output across multiple commands. Use when an agent must keep an SSH shell open, send commands incrementally, inspect prompts or streamed output, reuse one authenticated connection for a task, or safely start/stop a long-lived remote session for debugging, administration, deployment, log inspection, or interactive line-based wo…

— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-02loveslollipop-opencrow-ssh-async

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-02loveslollipop-opencrow-ssh-async)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ssh Async? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

OpenCROW I/O - SSH Async

Runtime preflight

Probe required commands with command -v and Python modules with importlib.util.find_spec before use. Prefer a PATH-resolved OpenCROW MCP helper or the ctf/sage environment when available, then the managed helper or system Python. If a capability is missing, stop that path safely and report the exact missing command or module.

Prefer the opencrow-ssh-mcp server for session lifecycle, reads, and writes. Fall back to scripts/sshx only when you need to inspect or debug the backend directly.

MCP First

  • Use toolbox_info, toolbox_verify, and toolbox_capabilities first.
  • Use the generic session tools:
  • session_start
  • session_send
  • session_read
  • session_status
  • session_stop
  • Keep one named session per host/task flow so the MCP server can return stable artifacts under /tmp/opencrow-ssh-async//.

Use scripts/sshx to manage long-lived SSH sessions instead of one-shot ssh invocations when you are operating outside MCP.

Workflow

  1. Start a named session to a remote host.
  2. Send shell input while the daemon keeps receiving remote output asynchronously.
  3. Read logs with --tail for recent context or --follow for streaming output.
  4. Stop the session explicitly when done.

Commands

# Start an interactive login shell
scripts/sshx start --name demo --host 10.0.0.5 --user ubuntu

# Start with a specific identity file and port
scripts/sshx start --name prod --host prod.example.com --user deploy --port 2222 \
  --identity ~/.ssh/deploy_ed25519

# Send a command to the open shell
scripts/sshx send --name prod --data 'uname -a' --newline

# Read recent output
scripts/sshx read --name prod --tail 60

# Follow output live
scripts/sshx read --name prod --follow

# Inspect metadata and process state
scripts/sshx status --name prod

# Stop the session
scripts/sshx stop --name prod

Operational Rules

  • Use one session per host/task flow so prompts, working directory, and shell state stay coherent.
  • Prefer key-based authentication. The helper runs ssh in batch mode and will fail fast instead of hanging on password prompts.
  • Append --newline for normal shell commands.
  • Read with --tail before --follow so prompt/output context is visible first.
  • Stop sessions explicitly to avoid leaving remote shells running.
  • If status reports running: false, inspect daemon.log and io.log before restarting.

Files and State

Session state lives at /tmp/opencrow-ssh-async//:

  • io.log: timestamped TX/RX events with escaped control characters
  • rx.raw: raw PTY output bytes from the SSH session
  • daemon.log: daemon stdout/stderr and launcher failures
  • meta.json: target metadata and SSH arguments
  • pid: daemon PID

Limitations

  • This tool is designed for line-oriented shell workflows, not full-screen TUIs such as vim, top, or less.
  • Password, OTP, and passphrase prompts are not supported because the session daemon is intentionally non-interactive during startup.
  • If the remote command disables prompts or uses unusual terminal control sequences, inspect rx.raw in addition to io.log.

References

  • For usage patterns and recovery steps, read references/patterns.md.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.